Local Multi-Head Channel Self-Attention for Facial Expression Recognition

TL;DR

This paper introduces LHC, a novel local multi-head channel self-attention module for CNNs, achieving state-of-the-art facial expression recognition results with lower complexity.

Contribution

The paper proposes a new channel-wise local self-attention module, LHC, specifically designed for computer vision, improving facial expression recognition performance.

Findings

Achieved new state-of-the-art on FER2013 dataset.

Lower computational complexity compared to previous methods.

Effective integration of LHC into CNNs enhances recognition accuracy.

Abstract

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the self-attention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily integrated in virtually every convolutional neural network and that is specifically designed for computer vision, the LHC: Local (multi) Head Channel (self-attention). LHC is based on two main ideas: first, we think that in computer vision the best way to leverage the self-attention paradigm is the channel-wise application instead of the more explored spatial attention and that convolution will not be replaced by attention modules like recurrent networks were in NLP; second, a local approach has the potential to better overcome the limitations of convolution than global attention. With LHC-Net we managed to achieve a new state of the art in the famous FER2013 dataset with a significantly lower complexity and impact on the "host" architecture in terms of computational cost when compared with the previous SOTA.